DocumentCode
3234129
Title
A novel algorithm for HMM word spotting performance evaluation and error analysis
Author
Marcus, Jeffrey N.
Author_Institution
Lab. for Comput. Sci., MIT, Cambridge, MA, USA
Volume
2
fYear
1992
fDate
23-26 Mar 1992
Firstpage
89
Abstract
A hidden Markov model (HMM) wordspotter is described. The emphasis is on the algorithms for HMM scoring and performance evaluation, which offer several advantages over those currently used. These advantages include the ability to: determine both the beginning and ending points of a spotted word, generate a smooth receiver operating characteristic (ROC) in a computationally efficient manner, and compare word spotters on the same task using a nonparametric significance test
Keywords
error analysis; hidden Markov models; speech recognition; HMM word spotting; algorithms; error analysis; hidden Markov model; nonparametric significance test; performance evaluation; receiver operating characteristic; scoring; speech recognition; Algorithm design and analysis; Character generation; Computer errors; Computer science; Error analysis; Hidden Markov models; Laboratories; Natural languages; Performance analysis; Speech enhancement;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on
Conference_Location
San Francisco, CA
ISSN
1520-6149
Print_ISBN
0-7803-0532-9
Type
conf
DOI
10.1109/ICASSP.1992.226113
Filename
226113
Link To Document